Stock Market Analysis

In [1]:
!pip install yfinance==0.1.67
!pip install pandas==1.3.3
!pip install requests==2.26.0
!mamba install bs4==4.10.0 -y
!pip install plotly==5.3.1
Collecting yfinance==0.1.67
  Downloading yfinance-0.1.67-py2.py3-none-any.whl (25 kB)
Requirement already satisfied: pandas>=0.24 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from yfinance==0.1.67) (1.3.4)
Collecting multitasking>=0.0.7
  Downloading multitasking-0.0.11-py3-none-any.whl (8.5 kB)
Requirement already satisfied: numpy>=1.15 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from yfinance==0.1.67) (1.20.3)
Requirement already satisfied: requests>=2.20 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from yfinance==0.1.67) (2.26.0)
Requirement already satisfied: lxml>=4.5.1 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from yfinance==0.1.67) (4.7.1)
Requirement already satisfied: python-dateutil>=2.7.3 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from pandas>=0.24->yfinance==0.1.67) (2.8.2)
Requirement already satisfied: pytz>=2017.3 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from pandas>=0.24->yfinance==0.1.67) (2021.3)
Requirement already satisfied: six>=1.5 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from python-dateutil>=2.7.3->pandas>=0.24->yfinance==0.1.67) (1.15.0)
Requirement already satisfied: idna<4,>=2.5 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from requests>=2.20->yfinance==0.1.67) (3.3)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from requests>=2.20->yfinance==0.1.67) (1.26.7)
Requirement already satisfied: charset-normalizer~=2.0.0 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from requests>=2.20->yfinance==0.1.67) (2.0.4)
Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from requests>=2.20->yfinance==0.1.67) (2022.6.15)
Installing collected packages: multitasking, yfinance
Successfully installed multitasking-0.0.11 yfinance-0.1.67
Collecting pandas==1.3.3
  Downloading pandas-1.3.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.5 MB)
     |████████████████████████████████| 11.5 MB 27.6 MB/s eta 0:00:01
Requirement already satisfied: python-dateutil>=2.7.3 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from pandas==1.3.3) (2.8.2)
Requirement already satisfied: numpy>=1.17.3 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from pandas==1.3.3) (1.20.3)
Requirement already satisfied: pytz>=2017.3 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from pandas==1.3.3) (2021.3)
Requirement already satisfied: six>=1.5 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from python-dateutil>=2.7.3->pandas==1.3.3) (1.15.0)
Installing collected packages: pandas
  Attempting uninstall: pandas
    Found existing installation: pandas 1.3.4
    Uninstalling pandas-1.3.4:
      Successfully uninstalled pandas-1.3.4
Successfully installed pandas-1.3.3
Requirement already satisfied: requests==2.26.0 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (2.26.0)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from requests==2.26.0) (1.26.7)
Requirement already satisfied: idna<4,>=2.5 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from requests==2.26.0) (3.3)
Requirement already satisfied: charset-normalizer~=2.0.0 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from requests==2.26.0) (2.0.4)
Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from requests==2.26.0) (2022.6.15)
/usr/bin/sh: mamba: command not found
Collecting plotly==5.3.1
  Downloading plotly-5.3.1-py2.py3-none-any.whl (23.9 MB)
     |████████████████████████████████| 23.9 MB 25.1 MB/s eta 0:00:01
Requirement already satisfied: tenacity>=6.2.0 in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from plotly==5.3.1) (8.0.1)
Requirement already satisfied: six in /opt/conda/envs/Python-3.9/lib/python3.9/site-packages (from plotly==5.3.1) (1.15.0)
Installing collected packages: plotly
  Attempting uninstall: plotly
    Found existing installation: plotly 5.1.0
    Uninstalling plotly-5.1.0:
      Successfully uninstalled plotly-5.1.0
Successfully installed plotly-5.3.1
In [2]:
import yfinance as yf
import pandas as pd
import requests
from bs4 import BeautifulSoup
import plotly.graph_objects as go
from plotly.subplots import make_subplots
In [3]:
def make_graph(stock_data, revenue_data, stock):
    fig = make_subplots(rows=2, cols=1, shared_xaxes=True, subplot_titles=("Historical Share Price", "Historical Revenue"), vertical_spacing = .3)
    stock_data_specific = stock_data[stock_data.Date <= '2021--06-14']
    revenue_data_specific = revenue_data[revenue_data.Date <= '2021-04-30']
    fig.add_trace(go.Scatter(x=pd.to_datetime(stock_data_specific.Date, infer_datetime_format=True), y=stock_data_specific.Close.astype("float"), name="Share Price"), row=1, col=1)
    fig.add_trace(go.Scatter(x=pd.to_datetime(revenue_data_specific.Date, infer_datetime_format=True), y=revenue_data_specific.Revenue.astype("float"), name="Revenue"), row=2, col=1)
    fig.update_xaxes(title_text="Date", row=1, col=1)
    fig.update_xaxes(title_text="Date", row=2, col=1)
    fig.update_yaxes(title_text="Price ($US)", row=1, col=1)
    fig.update_yaxes(title_text="Revenue ($US Millions)", row=2, col=1)
    fig.update_layout(showlegend=False,
    height=900,
    title=stock,
    xaxis_rangeslider_visible=True)
    fig.show()

Using the Ticker function enter the ticker symbol of the stock we want to extract data on to create a ticker object. The stock is Tesla and its ticker symbol is TSLA.

In [4]:
tesla = yf.Ticker("TSLA")

Using the ticker object and the function history extract stock information and save it in a dataframe named tesla_data. Set the period parameter to max so we get information for the maximum amount of time.

In [5]:
tesla_data = tesla.history(period="max")

Reset the index using the reset_index(inplace=True) function on the tesla_data DataFrame and display the first five rows of the tesla_data dataframe using the head function. Take a screenshot of the results and code from the beginning of Question 1 to the results below.

In [6]:
tesla_data.reset_index(inplace=True)
tesla_data.head()
Out[6]:
Date Open High Low Close Volume Dividends Stock Splits
0 2010-06-29 19.000000 25.000000 17.540001 23.889999 18783276.0 0 0.0
1 2010-06-30 25.959999 30.419201 23.299999 23.830000 17194394.0 0 0.0
2 2010-07-01 25.000000 25.920000 20.270000 21.959999 8216789.0 0 0.0
3 2010-07-02 23.000000 23.100000 18.709999 19.200001 5135795.0 0 0.0
4 2010-07-06 20.000000 20.000000 15.830000 16.110001 6852634.0 0 0.0

Use the requests library to download the webpage https://www.macrotrends.net/stocks/charts/TSLA/tesla/revenue. Save the text of the response as a variable named html_data.

In [7]:
import requests
url = " https://www.macrotrends.net/stocks/charts/TSLA/tesla/revenue"
html_data = requests.get(url).text

Parse the html data using beautiful_soup.

In [8]:
soup = BeautifulSoup(html_data, 'html5lib')

Using BeautifulSoup or the read_html function extract the table with Tesla Quarterly Revenue and store it into a dataframe named tesla_revenue. The dataframe should have columns Date and Revenue.

In [9]:
tesla_revenue = pd.DataFrame(columns=["Date", "Revenue"])
table = soup.find_all("tbody")[1]
rows = table.find_all("tr")
for row in rows:
    col = row.find_all("td")
    date = col[0].text
    revenue = col[1].text
    tesla_revenue =  tesla_revenue.append({"Date":date, "Revenue":revenue}, ignore_index=True)
tesla_revenue.tail()
Out[9]:
Date Revenue
48 2010-06-30 $28
49 2010-03-31 $21
50 2009-12-31
51 2009-09-30 $46
52 2009-06-30 $27
In [10]:
tesla_revenue["Revenue"] = tesla_revenue['Revenue'].str.replace(',|\$',"")
/tmp/wsuser/ipykernel_166/349343550.py:1: FutureWarning: The default value of regex will change from True to False in a future version.
  tesla_revenue["Revenue"] = tesla_revenue['Revenue'].str.replace(',|\$',"")

remove an null or empty strings in the Revenue column.

In [11]:
tesla_revenue.dropna(inplace=True)

tesla_revenue = tesla_revenue[tesla_revenue['Revenue'] != ""]

Display the last 5 row of the tesla_revenue dataframe using the tail function. Take a screenshot of the results.

In [12]:
tesla_revenue.tail()
Out[12]:
Date Revenue
47 2010-09-30 31
48 2010-06-30 28
49 2010-03-31 21
51 2009-09-30 46
52 2009-06-30 27

Using the Ticker function enter the ticker symbol of the stock we want to extract data on to create a ticker object. The stock is GameStop and its ticker symbol is GME.

In [13]:
game_stop = yf.Ticker("GME")

Using the ticker object and the function history extract stock information and save it in a dataframe named gme_data. Set the period parameter to max so we get information for the maximum amount of time.

In [14]:
gme_data = game_stop.history(period="max")
In [15]:
gme_data.reset_index(inplace=True)
gme_data.head()
Out[15]:
Date Open High Low Close Volume Dividends Stock Splits
0 2002-02-13 1.620128 1.693350 1.603296 1.691667 76216000 0.0 0.0
1 2002-02-14 1.712707 1.716074 1.670626 1.683250 11021600 0.0 0.0
2 2002-02-15 1.683250 1.687458 1.658002 1.674834 8389600 0.0 0.0
3 2002-02-19 1.666418 1.666418 1.578047 1.607504 7410400 0.0 0.0
4 2002-02-20 1.615920 1.662210 1.603296 1.662210 6892800 0.0 0.0
In [16]:
import requests
url = "https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-PY0220EN-SkillsNetwork/labs/project/stock.html"
html_data = response = requests.get(url).text
In [17]:
from bs4 import BeautifulSoup
soup = BeautifulSoup(html_data, "html5lib")
In [18]:
gme_revenue = pd.DataFrame(columns = ["Date", "Revenue"])
table = soup.find_all("tbody")[1]
rows = table.find_all("tr")
for row in rows:
    date = row.find_all("td")[0].text
    revenue = row.find_all("td")[1].text
    gme_revenue =  gme_revenue.append({"Date": date, "Revenue": revenue}, ignore_index=True)
gme_revenue.tail()
Out[18]:
Date Revenue
57 2006-01-31 $1,667
58 2005-10-31 $534
59 2005-07-31 $416
60 2005-04-30 $475
61 2005-01-31 $709
In [19]:
gme_revenue["Revenue"] = gme_revenue['Revenue'].str.replace(',|\$',"")
gme_revenue.dropna(inplace=True)

gme_revenue = gme_revenue[gme_revenue['Revenue'] != ""]
/tmp/wsuser/ipykernel_166/2914211459.py:1: FutureWarning: The default value of regex will change from True to False in a future version.
  gme_revenue["Revenue"] = gme_revenue['Revenue'].str.replace(',|\$',"")

Display the last five rows of the gme_revenue dataframe using the tail function. Take a screenshot of the results.

In [20]:
gme_revenue.tail()
Out[20]:
Date Revenue
57 2006-01-31 1667
58 2005-10-31 534
59 2005-07-31 416
60 2005-04-30 475
61 2005-01-31 709
In [21]:
make_graph(tesla_data, tesla_revenue, 'Tesla')
In [22]:
make_graph(gme_data, gme_revenue, 'GameStop')